October 2008
Intermediate to advanced
984 pages
30h 43m
English
Feature generation is of paramount importance in any pattern recognition task. Given a set of measurements, the goal is to discover compact and informative representations of the obtained data. A similar process is also taking place in the human perception apparatus. Our mental representation of the world is based on a relatively small number of perceptually relevant features. These are generated after processing a large amount of sensory data, such as the intensity and the color of the pixels of the images sensed by our eyes, and the power spectra of the sound signals sensed by our ears.
The basic approach followed in this chapter is to transform ...
Read now
Unlock full access